Research map / Multi-agent systems and games / LLM agents
COBRA: Context-Aware Bernoulli Neural Networks for Reputation Assessment
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the Bernoulli neural network instead of a fully connected feed-forward network (ablation) | COBRA · Web-service response-time dataset | prediction accuracy | Helped |
| Use the Bernoulli neural network instead of a fully connected feed-forward network (ablation) | COBRA · Web-service response-time dataset | training and prediction time | Helped |
| Use a fully connected feed-forward network instead of the Bernoulli neural network (ablation) | COBRA-GNB · Web-service response-time dataset | prediction accuracy | Hurt |
| Use a fully connected feed-forward network instead of the Bernoulli neural network (ablation) | COBRA · Web-service response-time dataset | overfitting | Hurt |
| Vary the model-encapsulation approach among decision tree, Gaussian Naive Bayes, and a hybrid (ablation) | COBRA · Web-service response-time dataset | prediction performance | No clear effect |
| Aggregate contextual model predictions with COBRA rather than the benchmark TRM systems | COBRA · Web-service response-time dataset | prediction accuracy | Helped |
| Use COBRA to aggregate advice when 51% of agents provide misleading models | COBRA · Simulated multi-agent system with 51% malicious agents | accuracy | Helped |
Closest papers by meaning
- To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems (NeurIPS 2026 · similarity 0.82)
- U-trustworthy Models. Reliability, Competence, and Confidence in Decision-Making (AAAI 2024 · similarity 0.79)
- Position: TrustLLM: Trustworthiness in Large Language Models (ICML 2024 · similarity 0.79)
- Trust-GRS: A Trustworthy Training Framework for Graph Neural Network Based Recommender Systems Against Shilling Attacks (AAAI 2025 · similarity 0.78)
- TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized Federated Learning (AAAI 2025 · similarity 0.78)
- POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM Agents (NeurIPS 2026 · similarity 0.78)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.